338 results about "Time–frequency analysis" patented technology

The invention provides an underground equipment fault real-time diagnosis method and system based on edge calculation, and relates to the technical field of coal mine safety production, and the method comprises the steps: collecting multi-modal data through a distributed sensor network, extracting multi-scale time sequence features, projecting the features to a Lie group manifold space, constructing a coupling mapping relation matrix, obtaining fusion features, and carrying out the real-time diagnosis of an underground equipment fault; and constructing a causal directed acyclic graph based on a topological connection relationship and a Granger causal coefficient, executing Bayesian probabilistic reasoning, determining an execution strategy in combination with entropy similarity matching, and performing deep time-frequency analysis and causal chain verification. High-precision real-time diagnosis of equipment faults in an underground complex environment is realized, and the fault early warning accuracy is improved.

The invention discloses a force control joint dynamic error compensation method based on Kalman filtering, and the method comprises the steps: collecting and preprocessing multi-source signal data, and forming a force control joint input data set; constructing an energy hierarchical Kalman filtering model, executing energy constraint correction and outputting state estimation; calculating a prediction residual error, carrying out time-frequency analysis, adjusting a compensation gain, and generating residual error information; torque and angular velocity signals are extracted, a semantic state is recognized, and semantic gating parameters are output; fusing the state estimation, the residual information and the semantic parameters to generate a dynamic compensation instruction signal; energy layer and residual information changes are monitored, self-calibration is triggered, and a feedback closed loop is formed. According to the invention, by introducing energy hierarchical Kalman filtering, time-frequency modulation compensation and a semantic gating feedback mechanism, dynamic error self-adaptive accurate compensation of the force control joint in a complex multi-disturbance environment is realized.

The invention belongs to the technical field of intelligent monitoring, and discloses a typhoon safety evaluation system and method for an ocean engineering structure. The method comprises the steps of collecting original data, preprocessing the original data to obtain standard data, and performing time-frequency analysis on the standard data to obtain time-frequency characteristics; performing analysis based on the time-frequency characteristics to obtain modal parameters; analyzing according to the modal parameters to obtain a non-linear state judgment result; carrying out damage positioning according to a non-linear state judgment result; carrying out residual safety life prediction according to a damage positioning result; the safety guarantee level of the ocean engineering structure in the typhoon period is remarkably improved.

The invention discloses a broadband oscillation characterization platform of a multi-chip power module and a near-field characteristic evaluation method, and belongs to the technical field of power electronics. The continuous operation condition of the power converter is decoupled into a series of discrete switching points, transient near-field radiation data of a to-be-tested power module under the discrete switching points are obtained through a double-pulse test, and near-magnetic field radiation signals are reconstructed; performing time-frequency analysis on the reconstructed near magnetic field radiation signal to generate a two-dimensional time-frequency matrix; and calculating a radiation energy entropy value based on the two-dimensional time-frequency matrix, fusing the radiation energy entropy value with the peak amplitude in the two-dimensional time-frequency matrix to generate a comprehensive EMI index for evaluating the broadband oscillation electromagnetic interference risk, and triggering EMI risk early warning when the comprehensive EMI index exceeds a threshold value. According to the method, the spectrum complexity is quantified through the radiation energy entropy, the multi-dimensional EMI risk assessment is carried out by fusing the peak amplitude of the time-frequency matrix, and the broadband oscillation in the multi-chip parallel power module can be accurately and efficiently represented.

The invention relates to a precise health monitoring method based on multi-source data fusion. The method comprises the following steps of 1, collecting multi-source data; step 2, data preprocessing; step 3, multi-source data fusion; 4, health analysis and decision making; step 5, dynamic weight adjustment; and step 6, feedback optimization. The hierarchical fusion strategy is adopted to process heterogeneous data, a machine learning algorithm is combined to establish an individualized health model, physiological state changes are tracked in real time, a targeted intervention scheme is generated, and in terms of technical implementation, the system supports collaborative decision making of various analysis models, including rule-based behavior reasoning, time sequence feature analysis and environment threshold judgment, and the system has the advantages of being simple in structure and convenient to use. The contribution degrees of information of different sources are balanced through an adaptive weight distribution mechanism, time-frequency analysis and dimension reduction technologies are fused in the feature extraction process, the dynamic mode of the health state is effectively captured, cross validation optimization is adopted in model training, and the reliability of an evaluation result is ensured.

A power transmission tower grounding resistance non-contact measurement method based on the electromagnetic coupling principle comprises the following steps that transmitting and receiving electromagnetic coupling coils are arranged around an iron tower grounding body, and geometric calibration and spatial positioning of a measurement area are completed by combining grounding grid structure parameters and soil conduction characteristics; injecting a high-frequency alternating-current excitation signal into the transmitting coil, and synchronously acquiring the amplitude and phase response of the induced voltage at a receiving coil end; carrying out filtering processing on the induction signal by adopting a time-frequency analysis and phase decoupling algorithm, and solving a function relationship between electromagnetic response and grounding impedance by combining a coupling equivalent model; based on experimental calibration data and scene parameters, a nonlinear mapping model of induction response and grounding resistance is constructed, and real-time inversion calculation is carried out by combining a solving result obtained in the third step. According to the invention, the real-time accurate measurement of the grounding resistance under the conditions of no power failure and no wire breakage is realized, and the safety, the operation convenience and the anti-interference capability in a complex environment in the measurement process are obviously improved.

The embodiment of the invention provides a switch cabinet partial discharge quantum sensing monitoring device. The device is applied to the technical field of power equipment monitoring, and comprises a light path regulation and excitation module which is used for generating and beam-splitting detection laser of a quantum sensor coupled to each Rydberg atom; the quantum electromagnetic induction module acts on Rydberg atoms and a partial discharge electromagnetic field, and fluorescence or absorption spectrum characteristics of atomic energy level transition are changed; extracting a weak discharge signal, and converting the weak discharge signal into an analyzable electric signal; the signal processing and diagnosis module is combined with spatial information acquired by a quantum sensor of doydberg atoms in a distributed manner, and a time-frequency analysis and pattern recognition algorithm is adopted to extract discharge characteristic quantity; partial discharge positioning, type identification and insulation state evaluation are realized based on the parameters, and a real-time monitoring result and early warning information are output. In this way, through deep fusion of quantum sensing and advanced signal processing, a high-precision and high-reliability technical solution is provided for power equipment state monitoring.

The invention provides an anomaly identification method and system for subway tunnel multi-source signal data, and relates to the technical field of subway tunnel safety monitoring, and the method comprises the steps: carrying out the Kalman filtering processing of multi-source sensing signal data monitored by a sensor in a subway tunnel, performing interpolation processing on the multi-source sensing signal data according to the obtained data sampling rate deviation to obtain alignment data; calling a multi-order rectangular self-convolution window to carry out time-frequency analysis on the alignment data to obtain windowed signal data, and carrying out window updating on the windowed signal data according to a current frequency estimation value of the windowed signal data to obtain to-be-detected signal data; and calling an anomaly detection model to perform anomaly recognition on the multi-source signal features extracted from the to-be-detected signal data to obtain an anomaly recognition result of the subway tunnel state. The method is used for solving the defects of low real-time performance and insufficient anomaly recognition precision in the sensor signal data processing and anomaly recognition process in the subway tunnel scene.

The invention discloses a non-contact method for measuring a three-dimensional flow velocity field in a pipeline based on acoustic Doppler, and the method comprises the steps: transmitting a focused sound beam into the pipeline, receiving an echo signal reflected by a scatterer in fluid, and generating a Doppler echo signal set covering different angles and depth positions; performing pulse compression and time-frequency analysis on the Doppler echo signal set, and calculating the sight flow velocity component of each point along the sound beam direction; calculating a three-dimensional flow velocity vector of each sampling point based on the coordinate position of each space sampling point and the corresponding sight line flow velocity component, and realizing decoupling of the flow velocity direction and size; according to the spatial distribution of the three-dimensional flow velocity vector on the section of the pipeline, a three-dimensional flow velocity field model in the pipeline is generated through interpolation fitting, and section flow and flow state characteristic parameters are calculated according to the model. According to the embodiment of the invention, the limitation that only two-dimensional or one-dimensional flow velocity can be measured in a traditional method can be broken through, and the spatial resolution and measurement precision of flow velocity field reconstruction in a complex flow state are improved.

The invention belongs to the field of non-intrusive power load monitoring, and discloses a non-intrusive power load identification method, which comprises the following steps of: constructing a load identification framework utilizing frequency domain characteristics, and aims to solve the problem that transient characteristics cannot be effectively applied in non-linear load identification in non-intrusive load monitoring. A current feature extraction technology based on fast Fourier transform and Hilbert-Huang transform and a classification method based on an extreme learning machine as a main body are used for training and testing a public data set to verify that the method is used for extracting transient load features and identifying nonlinear loads.

The invention relates to the field of power transmission line operation monitoring, in particular to a lead galloping real-time monitoring system based on Beidou high-precision positioning and multi-source data fusion, which comprises a data acquisition and preprocessing module, a data fusion and three-dimensional reconstruction module, an edge intelligent identification module and a cloud decision and collaborative management module, beidou RTK positioning data, micro-meteorological data and lead image data are synchronously obtained through an integrated monitoring device installed on the unmanned aerial vehicle in a live-line mode, and the positioning data are filtered and corrected; dynamically reconstructing a three-dimensional space form curve of the wire based on multi-source data fusion and physical parameters of the wire; performing time-frequency analysis on the lead motion characteristics, and identifying specific working condition types and severity levels; and an early warning decision instruction and a structured diagnosis report are generated at the cloud in combination with historical cases, operation rules, weather and power grid operation data. The method improves the monitoring precision and real-time performance of the operation state of the conductor and the perspectiveness of operation and maintenance decision, and is suitable for safe operation management of the power transmission line.

The invention discloses a multi-modal frequency domain enhanced critical prediction method and device. The method comprises the following steps: acquiring first data and second data; extracting a frequency domain amplitude spectrum, a phase spectrum and a multi-scale wavelet coefficient corresponding to each modal time sequence signal; extracting static features from the medical record data; fusing the static characteristics and the frequency domain amplitude spectrum, the phase spectrum and the multi-scale wavelet coefficient corresponding to each modal time sequence signal to obtain a multi-modal characteristic matrix; constructing a frequency enhancement prediction model; and inputting the multi-modal characteristic matrix into a frequency enhancement prediction model to obtain a prediction result output by the frequency enhancement prediction model, and fully capturing global frequency domain characteristics and local time domain details of the signal by integrating the multi-modal time sequence signal and medical record static data and combining time-frequency analysis. The accuracy and the real-time performance of illness state prediction of the critical patient are effectively improved, and then reliable data support is provided for clinical diagnosis and treatment decisions.

The invention discloses a carbon fiber prepreg laying layer defect detection method and system based on nonlinear guided waves, and the method comprises the steps: arranging excitation and receiving sensor arrays at the inner side and the outer side of a carbon fiber prepreg region, transmitting Hanning window modulation sine wave signals through the excitation sensor arrays, arranging an acoustic metamaterial layer on the surface of a detection region, and detecting the defects of the carbon fiber prepreg laying layer through the acoustic metamaterial layer. An excitation sensor array is divided into two groups to emit different phase signals, so that wave beams are focused at specified positions in a detection area and interact with each other, normalized time-frequency analysis is performed on reference signals and to-be-detected signals, second harmonic components and sideband frequency components are extracted, a relative nonlinear coefficient is calculated based on a signal difference value, and the relative nonlinear coefficient is calculated. And processing and receiving full matrix data of the sensor array by adopting a full focusing method, and reconstructing a nonlinear coefficient distribution image in the carbon fiber prepreg to carry out defect positioning and quantitative evaluation on the acoustic metamaterial layer. According to the invention, accurate and reliable detection and early warning of micro-defects in the carbon fiber prepreg laying process are realized.

The invention discloses an immersive cinema dynamic content adaptation control method based on multi-modal fusion, and the method comprises the steps: collecting at least one non-contact physiological signal of a target audience seat area in real time, the physiological signal comprising a respiratory wave signal collected by a millimeter wave radar or a photoplethysmography signal collected by a near-infrared photoelectric sensor; performing time-frequency analysis on the physiological signal, and extracting a physiological wake-up characterization value in a current time window; the physiological wake-up characterization value comprises a heart rate variability change rate and a heart rate deviation value; constructing a dynamic damping adjustment model, and calculating a virtual damping coefficient of the seat movement system at the current moment based on the physiological wake-up characterization value; and the virtual damping coefficient is converted into an execution instruction of a seat motion controller, and damping force output of the motion platform is adjusted in real time. The technical problem that the pre-programmed motion feedback is disjointed with the real-time physiological and psychological state of the audience can be solved, the experience adaptability and comfort of the cinema seat are improved, and the system safety is improved.

The invention relates to the technical field of sensor network chips, and discloses a gas safety monitoring method and system based on multi-sensor fusion, and the method comprises the steps: obtaining mixed signal data, carrying out the decomposition and recognition of the mixed signal data, extracting interference components, and carrying out the filtering, and obtaining a preliminary filtering signal; executing time-frequency analysis to construct a two-dimensional time-frequency characteristic spectrum, identifying an interference area and evaluating interference intensity, and filtering to obtain a pure intermediate signal; constructing a multi-dimensional frequency feature set based on the signal, extracting an abnormal feature subset, and completing equipment mapping and clustering to obtain a marked component set; obtaining a time domain fragment, carrying out residual analysis to generate an interference distribution map, and extracting abnormal feature scores to form a risk score sequence; smoothing the sequence, constructing trend features and grading risk levels; and finally, mapping the alarm signal, carrying out coding verification and transmission, and outputting a final early warning. According to the method, accurate extraction and graded early warning of gas leakage signals in a complex interference environment can be realized.

The invention discloses a sound signal processing method and device, equipment and a storage medium, and belongs to the technical field of audio processing. According to the invention, sound signal noise reduction with noise suppression and target signal reservation is realized. The method comprises the following steps: after acquiring a sound signal collected in a running state of mechanical equipment, firstly performing time-frequency analysis on the sound signal; then, a noise determination threshold is automatically determined based on the logarithmic magnitude spectrum of the sound signal, and noise estimation is performed based on the determined noise determination threshold. According to the scheme, a completely data-driven parameter selection mechanism is realized, and manual parameter or threshold setting is not needed, so that the automation degree is improved, the unreliability of manual parameter or threshold setting is avoided, and the accuracy and robustness of noise estimation are enhanced. In addition, the noise-reduced sound signal does not comprise noise components, so that the accuracy and reliability of subsequent operation state recognition and fault diagnosis of the mechanical equipment are ensured.

The invention discloses a water turbine governor fault modeling and parameter optimization method based on iterative learning control. The method comprises the following steps: S1, system dynamics modeling; s2, iterative learning parameter updating, wherein a water turbine governor fault diagnosis method based on iterative learning control realizes progressive identification of fault features through periodically correcting model parameters; s3, fault feature extraction: calculating a residual signal of an actual output and a model predicted value, performing time-frequency analysis on the residual signal by adopting improved Morlet wavelet transform, and extracting an energy entropy feature and a time domain statistical feature; s4, fault diagnosis and dynamic optimization: based on the extracted fault features, fault detection and classification are realized through a three-level linkage decision mechanism, a dynamic adjustment strategy is introduced to carry out online optimization on a diagnosis rule base, and fault modeling and parameter optimization closed loop are completed; according to the method, the problem of modeling misalignment of a traditional method under a nonlinear working condition is effectively solved.

The invention provides a frictional wear acoustic emission detection method based on a shear wave sensor, which comprises the following steps: determining the frequency response range of the shear wave sensor and designing the shear wave sensor according to the requirements of the material characteristics of a friction pair, different working condition scenes and monitoring precision; a designed shear wave sensor is installed on one side of a non-contact surface of a friction pair in a self-transmitting and self-receiving mode, and a frictional wear monitoring system is built by combining with the shear wave sensor; shear wave acoustic emission signals and mechanical signals collected in a frictional wear monitoring system are synchronously stored, collected data are analyzed by adopting a method of combining time domain analysis, frequency domain analysis and time-frequency analysis, a corresponding relation between signal characteristics and frictional wear states is established, and accurate identification of shear damage is realized. According to the invention, the in-situ, real-time and high-precision monitoring of the shear damage in the friction wear process is realized by optimizing the type of the sensor and building a friction wear monitoring system.

The invention relates to the field of signal processing, and provides a defibrillator human body shake detection method and system fusing electrocardio and transthoracic impedance in order to solve the problems that the human body shake false alarm rate is high, the human body shake detection precision is low and the reliability is poor when a patient is in a motion state. The defibrillator human body shaking detection method fusing electrocardio and transthoracic impedance comprises the steps that the human body shaking probability of impedance judgment is calculated, and the human body shaking probability of time-frequency analysis is obtained by combining the probability of electrocardio noise; obtaining a human body shaking probability output by the deep learning model through the deep learning model; calculating the confidence coefficient of the deep learning model according to the human body shaking probability output by the deep learning model, and adaptively matching a human body shaking probability calculation strategy to obtain a final human body shaking probability; and comparing the final human body shaking probability with a preset judgment threshold, and determining a human body shaking state. The human body shaking false alarm rate of a patient in a motion state can be reduced, and the human body shaking detection precision and reliability are improved.

The present application relates to the technical field of bridge track health monitoring, in particular to a high-speed rail bridge health monitoring method, medium and equipment based on an interferometric radar. The method comprises: identifying the driving lane of the train on the bridge through the interferometric radar; based on the driving lane, obtaining the bridge data required for health monitoring when the train passes through the bridge through the interferometric radar; processing the bridge data and extracting the product function; analyzing the product function, selecting the effective product function; performing time-frequency analysis on the effective product function to obtain the time-frequency pattern of the bridge data, and performing health monitoring on the high-speed rail bridge according to the time-frequency pattern. According to the bridge signal collected by the interferometric radar, the driving lane of the high-speed train is determined, the vibration characteristics of the bridge are further analyzed through the processing of RLMD and SET, the clear time-frequency pattern is obtained, and the time-frequency characteristics of the bridge are determined according to the time-frequency pattern, thereby providing a reliable method for health monitoring during the driving of the high-speed train.

This invention relates to the field of precision mechanical control technology, specifically to a method based on a magnetoelectric converter and linearity control. The method includes: acquiring raw magnetic induction data through a magnetoelectric converter; obtaining a three-dimensional magnetic field distribution through electromagnetic field spatial mapping and extracting the axial gradient vector field; constructing a virtual magnetic streamline model based on this to identify local disturbance regions where magnetic field distortion exceeds a threshold; performing multi-scale time-frequency analysis on the data in this region to separate high-frequency fluctuations caused by mechanical vibration and low-frequency drift components caused by thermal deformation; inputting the two components into a cross-coupled compensation decision network to generate high-frequency suppression commands and low-frequency compensation trajectories, which are then merged to form a comprehensive drive signal for compensation. This method can accurately locate the source of linearity disturbance and perform targeted decoupling control of errors from different physical sources, improving control accuracy and stability under complex operating conditions.

The invention discloses a guided wave detection and quantitative evaluation method for submarine pipeline routing deviation. The method comprises the steps that S1, an excitation end module periodically injects stable guided wave signals into a pipeline; s2, an annular receiving module for synchronously receiving signals in the whole annular direction is installed at a terminal of the pipeline, and guided wave signals propagated for a long distance are accurately captured; s3, filtering and enhancing the originally collected noisy signals; s4, performing time-frequency analysis and waveform inversion on the received signal, and respectively extracting: calculating the equivalent curvature radius of the offset section according to the propagation velocity change; extracting phase lag information according to the phase change, and calculating a vibration path increment; calculating the overall transmission loss according to the amplitude attenuation degree; and S5, establishing a comprehensive identification criterion fusing the three types of feature parameters. The low-attenuation long-distance propagation characteristic of the L (0, 1) mode is utilized, the excitation device and the receiving array are arranged at the two ends of the pipeline, and online periodic remote monitoring under the non-stop production state is achieved.

The invention relates to the field of numerical control machining data processing, in particular to a multi-axis linkage numerical control lathe machining data processing method and system. Comprising the following steps: acquiring vibration information, performing time-frequency analysis, and extracting energy change and instantaneous peak value characteristics in a preset high-frequency band; the features are compared with a preset judgment basis, an early sign of flutter is recognized, and when flutter is recognized, a machining parameter adjusting instruction for the rotating speed of the main shaft, the feeding speed and / or the cutting depth is generated; and the adjusted vibration information is obtained for time-frequency analysis, the flutter suppression effect is evaluated, machining parameters are further adjusted according to the flutter suppression effect, and / or an early warning or shutdown alarm is given out, so that closed-loop active suppression control over microcosmic cutting flutter is formed. The problems that due to the fact that a multi-axis linkage numerical control lathe cannot capture key and instantaneous high-frequency vibration mode information in a data collection and analysis frame, tool abrasion prediction is not accurate, the machining quality is reduced, the workpiece rejection rate is increased, and the production efficiency is reduced are solved.

This invention discloses a multi-scale time-frequency analysis method and system for ocean current meter signal processing, relating to the field of marine information processing. The method includes: S1: acquiring raw data and performing physical benchmark correction to obtain three-dimensional current velocity data and basic mass labels; S2: extracting first and second features from the three-dimensional current velocity data through spatiotemporal decoupling; S3: fusing and separating the three-dimensional current velocity data based on the first and second features to obtain an optimized set of flow field parameters, and generating the uncertainty of each parameter by combining the basic mass labels and error source information; S4: performing comprehensive quality assessment and grading based on the first and second features and the uncertainty, outputting a data product with mass labels and uncertainty information. By extracting spatiotemporal dual-dimensional features and using them to guide signal fusion and quality assessment, highly robust processing of ocean current data and end-to-end quality traceability are achieved, significantly improving the reliability of the data product.

This invention discloses an inversion method for S-wave velocity structure based on dense micromotion observations, belonging to the field of geophysical exploration and engineering geological exploration technology. The method includes: acquiring micromotion data; performing segmented preprocessing and cross-correlation calculations; constructing a phase consistency metric function based on the instantaneous phase information of the cross-correlation function for each time period; generating adaptive weighting coefficients; and then constructing an empirical Green's function through weighted superposition. Subsequently, time-frequency analysis is performed to obtain a time-frequency energy map; preliminary extraction of candidate dispersion velocities for each frequency is performed, and their comprehensive confidence level is calculated; after verification, a reliable dispersion curve is obtained. Based on the dispersion curve, a model parameter vector is established, and a joint objective function is constructed. A differential evolution algorithm is used for parallel global optimization inversion to obtain a one-dimensional S-wave velocity structure model below each station pair. The one-dimensional models are interpolated and fused to generate a two-dimensional S-wave velocity structure profile. This invention has the advantages of high inversion stability, high computational efficiency, and a high degree of automation.

The present disclosure relates to the technical field of automatic intelligent auxiliary detection of electrocardiogram, and proposes a self-supervised neural network learning heartbeat classification method and system based on pre-labeling, which comprises the following steps: preprocessing the acquired electrocardiogram data to obtain heartbeat data; performing time-frequency analysis on the acquired one-dimensional heartbeat data to convert it into a two-dimensional time-frequency graph; inputting the converted two-dimensional time-frequency graph into a trained self-supervised learning network model to classify the heartbeat data and obtain a classification result; the self-supervised learning network model is trained in combination with the SimCLR method and the clustering method, so that the loss function term changes from one item to two items, the learning effect is strengthened, and the classification accuracy of the heartbeat data can be improved.

The invention discloses a sparse inversion time-frequency analysis method based on a semi-norm, and the method comprises the steps: designing a window function for original seismic data, so as to reduce the influence of a window truncation effect on time-frequency analysis; constructing a Fourier forward matrix and a windowed Fourier matrix according to the size of the window function and the size of the frequency spectrum; in-window seismic data extraction is carried out on sample points of single-channel seismic data, and a semi-norm constrained time-frequency spectrum sparse inversion objective function is constructed; performing time-frequency spectrum coefficient inversion on the time-frequency spectrum sparse inversion target function to obtain a sparse inversion time-frequency spectrum result of the seismic data in the window; and sliding the sample points of the seismic data to repeat the process, and performing time-frequency spectrum sparse inversion on all the seismic data to obtain a final time-frequency analysis result. According to the method, the time-frequency spectrum precision and the time-frequency focusing property of the seismic signal can be effectively improved, and a time-frequency analysis result with higher precision is provided for subsequent reservoir identification and oil and gas prediction work.

The present application relates to a method for detecting loosening of ceramic dewatering elements for papermaking based on vibration spectrum analysis, aiming to solve the problems of difficult early identification of loosening and weak anti-working condition interference ability of ceramic dewatering elements in the running of the paper machine wire section. The scheme synchronously collects vibration signals and multi-dimensional working condition parameters, generates a structured frequency spectrum through time-frequency analysis and power spectrum density processing, and then fuses the knowledge base to match the reference structure template, realizing the topological edit distance quantization of the measured and reference frequency spectrum. Combined with the fuzzy rule engine, the different loosening degrees are dynamically weighted and inferred, and the positioning accuracy is improved through graph structure evolution trajectory analysis and high-resolution order tracking. The technology has high robustness and early loosening identification ability, which is beneficial to improve the intelligentization and intelligent decision level of the health monitoring of the clean production line ceramic elements.

This invention discloses a photovoltaic system islanding detection method and system based on Santlet transform and Ridglet probabilistic neural network. The method includes: collecting historical voltage data of the photovoltaic inverter, preprocessing it, and then sequentially acquiring the data to be analyzed using a sliding window; performing time-frequency analysis using Santlet continuous wavelet transform to obtain the corresponding time-frequency spectrum; extracting multi-dimensional time-frequency feature vectors and inputting them into a trained Ridglet probabilistic neural network classification model to obtain the corresponding probability values; if the probability value is greater than a probability threshold, it is determined that the photovoltaic system has experienced islanding, and a trip signal is generated and sent to the grid-connected circuit breaker to disconnect it. This invention significantly improves the accuracy, speed, and reliability of islanding detection, effectively reduces the detection blind zone, and has good adaptability to complex power grid environments.

The invention discloses an electric power big data bad data detection and elimination method based on a fusion model, and the method comprises the steps: carrying out the normalization preprocessing of multi-source electric power data, so as to obtain standardized data; and carrying out dynamic denoising on the standardized data based on the K-LSTM model. And carrying out time-frequency analysis on the de-noised data based on a CT-Transform model, and extracting global and local features. And finally, rejecting bad data according to a model preset threshold. And introducing a learning feedback mechanism, and dynamically optimizing a threshold value to output safe and credible data. According to the method, the advantages that the LSTM is good at capturing a data time sequence dependency relationship, the CNN is good at extracting local time-frequency features, and the Transformer is good at capturing global time-space association are fused, so that the problem that a single LSTM is insufficient in high-frequency noise suppression capability and lacks a global view angle is effectively solved, and meanwhile, the limitation that a single CNN is insufficient in long-time dependency description and a single Transformer is insufficient in attention to local details is made up; and accurate detection and elimination of bad electric power data in a complex environment are realized.